Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1354 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3489. Min Range: -3.3489

Max Act: 3.3489. Min Act: -0.0000

Data Index: 329142 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 3.3489. Min Range: -3.3489

Max Act: 3.2889. Min Act: -0.0000

Data Index: 655023 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.9658. Min Act: -0.0000

Data Index: 119330 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 3.3489. Min Range: -3.3489

Max Act: 3.0842. Min Act: -0.0000

Data Index: 1206179 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 3.3489. Min Range: -3.3489

Max Act: 3.0502. Min Act: -0.0000

Data Index: 1014466 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 3.3489. Min Range: -3.3489

Max Act: 3.0141. Min Act: -0.0000

Data Index: 1580613 (Python Code)

Max Activating Token Index: 183

Text #6

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.9817. Min Act: -0.0000

Data Index: 110808 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 3.3489. Min Range: -3.3489

Max Act: 3.0102. Min Act: -0.0000

Data Index: 421355 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.8926. Min Act: -0.0000

Data Index: 1237722 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.6191. Min Act: -0.0000

Data Index: 9556 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.6491. Min Act: -0.0000

Data Index: 896725 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.7276. Min Act: -0.0000

Data Index: 899470 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.6116. Min Act: -0.0000

Data Index: 728539 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.5950. Min Act: -0.0000

Data Index: 18179 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.6853. Min Act: -0.0000

Data Index: 1404217 (Python Code)

Max Activating Token Index: 52

Text #15

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.6372. Min Act: -0.0000

Data Index: 592332 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.7818. Min Act: -0.0000

Data Index: 410485 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.6343. Min Act: -0.0000

Data Index: 66665 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.5406. Min Act: -0.0000

Data Index: 775859 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 3.3489. Min Range: -3.3489

Max Act: 2.5576. Min Act: -0.0000

Data Index: 527116 (C4 (Web Text))

Max Activating Token Index: 114